© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13119
    Prev
    Next
    INDEX
    Explanations

    absolute value $| |$ and rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —with
    -0.06
    emus
    -0.06
    +w
    -0.06
    γοÏħ
    -0.06
    .land
    -0.06
    пиÑĤа
    -0.06
    gw
    -0.06
    encrypt
    -0.06
    _eg
    -0.06
    /of
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮçļĦæĺ¯
    0.09
    å¥½å·¥ä½ľ
    0.08
    çļĦä¸ĢåĪĩéĥ½
    0.07
    çī¹çĤ¹å°±æĺ¯
    0.07
    åĨħ容åĮħæĭ¬
    0.07
     bowiem
    0.07
    çļĦè¯Ħä»·æĺ¯
    0.07
    ä¹ĭå¤Ħåľ¨äºİ
    0.07
    æ³ķæĺ¯
    0.07
     ìĤ¬ëŀĮëĵ¤ìĿĢ
    0.07
    Activations Density 0.013%

    No Known Activations